Flex inference

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="Analyze this dataset for trends...",
    service_tier='flex'
)
print(interaction.output_text)

import { GoogleGenAI } from '@google/genai';

const client = new GoogleGenAI({});

async function main() {
    const interaction = await client.interactions.create({
        model: 'gemini-3.8-flash',
        input: 'Analyze this dataset for trends...',
        service_tier: 'flex'
    });
    console.log(interaction.output_text);
}
await main();

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.ServiceTier;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.of("Analyze this dataset for trends..."))
        .serviceTier(ServiceTier.FLEX)
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

System.out.println(interaction.outputText().orElse(""));

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model:       interactions.Model("gemini-3.8-flash"),
            Input:       interactions.NewInteractionsInput("Analyze this dataset for trends..."),
            ServiceTier: interactions.ServiceTierFlex.ToPointer(),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -d '{
      "model": "gemini-3.8-flash",
      "input": "Analyze this dataset for trends...",
      "service_tier": "flex"
  }'

from google import genai

client = genai.Client(http_options={"timeout": 900000})

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="why is the sky blue?",
    service_tier="flex",
)

import { GoogleGenAI } from '@google/genai';

const client = new GoogleGenAI({});

async function main() {
    const interaction = await client.interactions.create({
        model: "gemini-3.8-flash",
        input: "why is the sky blue?",
        service_tier: "flex",
    }, {timeout: 900000});
}

await main();

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.ServiceTier;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.types.HttpOptions;

Client client =
    Client.builder()
        .httpOptions(HttpOptions.builder().timeout(900000).build())
        .build();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.of("why is the sky blue?"))
        .serviceTier(ServiceTier.FLEX)
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

package main

import (
    "context"
    "log"
    "time"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, &genai.ClientConfig{
        HTTPOptions: genai.HTTPOptions{
            Timeout: genai.Ptr(15 * time.Minute),
        },
    })
    if err != nil {
        log.Fatal(err)
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model:       interactions.Model("gemini-3.8-flash"),
            Input:       interactions.NewInteractionsInput("why is the sky blue?"),
            ServiceTier: interactions.ServiceTierFlex.ToPointer(),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    _ = res
}

import time
from google import genai

client = genai.Client()

def call_with_retry(max_retries=3, base_delay=5):
    for attempt in range(max_retries):
        try:
            return client.interactions.create(
                model="gemini-3.8-flash",
                input="Analyze this batch statement.",
                service_tier="flex",
            )
        except Exception as e:
            if attempt < max_retries - 1:
                delay = base_delay * (2 ** attempt) # Exponential Backoff
                print(f"Flex busy, retrying in {delay}s...")
                time.sleep(delay)
            else:
                print("Flex exhausted, falling back to Standard...")
                return client.interactions.create(
                    model="gemini-3.8-flash",
                    input="Analyze this batch statement."
                )

interaction = call_with_retry()
print(interaction.output_text)

import { GoogleGenAI } from '@google/genai';

const ai = new GoogleGenAI({});

async function sleep(ms) {
  return new Promise(resolve => setTimeout(resolve, ms));
}

async function callWithRetry(maxRetries = 3, baseDelay = 5) {
  for (let attempt = 0; attempt < maxRetries; attempt++) {
    try {
      console.log(`Attempt ${attempt + 1}: Calling Flex tier...`);
      const interaction = await ai.interactions.create({
        model: "gemini-3.8-flash",
        input: "Analyze this batch statement.",
        service_tier: 'flex',
      });
      return interaction;
    } catch (e) {
      if (attempt < maxRetries - 1) {
        const delay = baseDelay * (2 ** attempt);
        console.log(`Flex busy, retrying in ${delay}s...`);
        await sleep(delay * 1000);
      } else {
        console.log("Flex exhausted, falling back to Standard...");
        return await ai.interactions.create({
          model: "gemini-3.8-flash",
          input: "Analyze this batch statement.",
        });
      }
    }
  }
}

async function main() {
    const interaction = await callWithRetry();
    console.log(interaction.output_text);
}

await main();

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.ServiceTier;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();

int maxRetries = 3;
int baseDelay = 5;
Interaction interaction = null;

for (int attempt = 0; attempt < maxRetries; attempt++) {
  try {
    CreateModelInteraction flexParams =
        CreateModelInteraction.builder()
            .model(Model.of("gemini-3.8-flash"))
            .input(InteractionsInput.of("Analyze this batch statement."))
            .serviceTier(ServiceTier.FLEX)
            .build();
    interaction =
        client.interactions.create(CreateInteractionRequestBody.of(flexParams)).interaction().get();
    break;
  } catch (Exception e) {
    if (attempt < maxRetries - 1) {
      int delay = baseDelay * (1 << attempt); // Exponential Backoff
      System.out.println("Flex busy, retrying in " + delay + "s...");
      Thread.sleep(delay * 1000L);
    } else {
      System.out.println("Flex exhausted, falling back to Standard...");
      CreateModelInteraction standardParams =
          CreateModelInteraction.builder()
              .model(Model.of("gemini-3.8-flash"))
              .input(InteractionsInput.of("Analyze this batch statement."))
              .build();
      interaction =
          client
              .interactions
              .create(CreateInteractionRequestBody.of(standardParams))
              .interaction()
              .get();
    }
  }
}

if (interaction != null) {
  System.out.println(interaction.outputText().orElse(""));
}

package main

import (
    "context"
    "fmt"
    "log"
    "time"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    maxRetries := 3
    baseDelay := 5
    var interaction *interactions.Interaction

    for attempt := 0; attempt < maxRetries; attempt++ {
        res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
            Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
                Model:       interactions.Model("gemini-3.8-flash"),
                Input:       interactions.NewInteractionsInput("Analyze this batch statement."),
                ServiceTier: interactions.ServiceTierFlex.ToPointer(),
            }),
        })
        if err == nil {
            interaction = res.Interaction
            break
        }

        if attempt < maxRetries-1 {
            delay := baseDelay * (1 << attempt) // Exponential Backoff
            fmt.Printf("Flex busy, retrying in %ds...\n", delay)
            time.Sleep(time.Duration(delay) * time.Second)
        } else {
            fmt.Println("Flex exhausted, falling back to Standard...")
            stdRes, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
                Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
                    Model: interactions.Model("gemini-3.8-flash"),
                    Input: interactions.NewInteractionsInput("Analyze this batch statement."),
                }),
            })
            if err != nil {
                log.Fatal(err)
            }
            interaction = stdRes.Interaction
        }
    }

    if interaction != nil && interaction.OutputText != nil {
        fmt.Println(*interaction.OutputText)
    }
}